java实现敏感词过滤,简单实例,dfa算法
最近在看黑马的视频学习的时候,看到了,自定义敏感词过滤的,感觉蛮有意思的,记录一下。
直接上实例
- 第一步初始化敏感词(可以写死,当然在开发的时候,是存在表里的,然后拿出来,业务人员自己维护一套敏感词)
- 拿到你需要检测的字符串
- 校验就行了
package com.example.demo.util;import java.util.*;public class SensitiveWordUtil {public static Map<String, Object> dictionaryMap = new HashMap<>();/*** 生成关键词字典库* @param words* @return*/public static void initMap(Collection<String> words) {if (words == null) {System.out.println("敏感词列表不能为空");return ;}// map初始长度words.size(),整个字典库的入口字数(小于words.size(),因为不同的词可能会有相同的首字)Map<String, Object> map = new HashMap<>(words.size());// 遍历过程中当前层次的数据Map<String, Object> curMap = null;Iterator<String> iterator = words.iterator();while (iterator.hasNext()) {String word = iterator.next();curMap = map;int len = word.length();for (int i =0; i < len; i++) {// 遍历每个词的字String key = String.valueOf(word.charAt(i));// 当前字在当前层是否存在, 不存在则新建, 当前层数据指向下一个节点, 继续判断是否存在数据Map<String, Object> wordMap = (Map<String, Object>) curMap.get(key);if (wordMap == null) {// 每个节点存在两个数据: 下一个节点和isEnd(是否结束标志)wordMap = new HashMap<>(2);wordMap.put("isEnd", "0");curMap.put(key, wordMap);}curMap = wordMap;// 如果当前字是词的最后一个字,则将isEnd标志置1if (i == len -1) {curMap.put("isEnd", "1");}}}dictionaryMap = map;}/*** 搜索文本中某个文字是否匹配关键词* @param text* @param beginIndex* @return*/private static int checkWord(String text, int beginIndex) {if (dictionaryMap == null) {throw new RuntimeException("字典不能为空");}boolean isEnd = false;int wordLength = 0;Map<String, Object> curMap = dictionaryMap;int len = text.length();// 从文本的第beginIndex开始匹配for (int i = beginIndex; i < len; i++) {String key = String.valueOf(text.charAt(i));// 获取当前key的下一个节点curMap = (Map<String, Object>) curMap.get(key);if (curMap == null) {break;} else {wordLength ++;if ("1".equals(curMap.get("isEnd"))) {isEnd = true;}}}if (!isEnd) {wordLength = 0;}return wordLength;}/*** 获取匹配的关键词和命中次数* @param text* @return*/public static Map<String, Integer> matchWords(String text) {Map<String, Integer> wordMap = new HashMap<>();int len = text.length();for (int i = 0; i < len; i++) {int wordLength = checkWord(text, i);if (wordLength > 0) {String word = text.substring(i, i + wordLength);// 添加关键词匹配次数if (wordMap.containsKey(word)) {wordMap.put(word, wordMap.get(word) + 1);} else {wordMap.put(word, 1);}i += wordLength - 1;}}return wordMap;}public static void main(String[] args) {List<String> list = new ArrayList<>();list.add("私人侦探");list.add("信用卡提现");list.add("广告代理");//初始化敏感词库initMap(list);String content="江户川柯南私人侦探,可以帮你解决:商务调查,要账清债,企业打假,寻人找人,财产调查,私人调查,电话:12345678901";//文本中查找是否包含敏感词Map<String, Integer> map = matchWords(content);if(map.size() > 0){System.out.println(map);}else {System.out.println("没有找到敏感词");}}
}